Eye remote control¶

This project is developed based on the Quectel Pi M2 Smart Single-Board Computer, leveraging its powerful computing capabilities and multimedia processing to achieve low-latency, high-accuracy eye tracking functionality.

The Eye Remote Control is an intelligent control system that manages video playback by detecting the user’s eye state: it continues playing when the user is looking at the screen and automatically pauses when the user closes their eyes or leaves the screen.

Core Features:

When the system detects that the user’s eyes are open and focused on the screen, it automatically plays or maintains video playback.
When the system detects that the user has closed their eyes, shifted their gaze, or left the screen, it immediately pauses the current video.

../../../_images/image_AXlLbVi9BoxZhVxZV21ctkU2nHg.webp

Development Resources¶

The development accessories are for reference only. Different development environments may vary. For example, if you develop via SSH remote connection, a USB dock may not be required, and the display can be substituted as needed.

Development Accessories List¶

Accessory	Quantity	Specifications
Quectel Pi M2 Smart Single-Board Computer	1	-
USB-C Power Cable & Charger	1	Official 45W USB Type-C Power Supply for Raspberry Pi 5, White Color, US Plug
HDMI Type-A Male Cable	1	HDMI 2.0; cable length 1 m; connectors: HDMI-A (male) to HDMI-A (male)
Ethernet Cable	1	Length: 1m; Speed: Gigabit
USB Camera Module	1	UGREEN HD USB Camera with Microphone (2K 4MP Auto Focus)
Display	1	24-inch HDMI Monitor

Accessories Reference Photo¶

../../../_images/image_CvcHb3sSKoMzmIxhClpcODVKnGX.webp

Quick Start¶

Preparation¶

The Quectel Pi M2 Smart Single-Board Computer comes pre-installed with the Debian 13 system image, so there is no need to flash the image again. Simply follow the steps below.

Hardware Connection¶

Complete all the following hardware connections. The numbering corresponds to the interface diagram:

../../../_images/image_CkvzbRZDzosuTCxr7AFcHKDfnRY.webp

Display Connection: Choose the connection method based on your monitor’s interface. Here we use Option 2: connect one end of the Micro HDMI cable to the main board’s Micro HDMI port and the other end to the monitor’s HDMI port.
1. Option 1 (HD): Connect one end of the FPC ribbon cable to the MIPI port on the Quectel Pi M2, and the other end to the monitor’s MIPI port. Refer to the MIPI for details.
2. Option 2 (Compatible): Connect one end of the HDMI cable to the HDMI port on the Quectel Pi M2, and the other end to the monitor’s HDMI port.
Network Connection: Connect the Quectel Pi M2 Ethernet port to the router’s LAN port using an Ethernet cable.
Peripheral Connection: Plug the USB keyboard, mouse, and USB camera into the USB-A ports on the Quectel Pi M2. For wireless keyboard/mouse, simply plug the receiver into a USB port.
Power Connection: Finally, plug the USB-A end of the power cable into the power adapter, and the USB-C end into the power port on the Quectel Pi M2.

Project Setup¶

Open a terminal on the Smart Single-Board Computer and clone the project code using git.

sudo apt update
sudo apt install -y git
git clone https://github.com/Quectel-Pi/demo-eye-remote-control.git

After execution, a demo-eye-remote-control folder should be generated in the current directory.

Run the following commands sequentially in the terminal on the Smart Single-Board Computer. If the terminal displays Deployment complete, the deployment is successful.

cd demo-eye-remote-control
sudo chmod 755 install.sh
./install.sh

If an error occurs during the execution of ./install.sh, or if the terminal does not display “Deployment complete”, do not proceed with the subsequent steps. First verify that the network connection is working, then return to the project root directory and re-run install.sh.

Open a new terminal and verify the Python version. An output of Python 3.10.15 indicates a successful installation.

python3 --version

Running the Program¶

Navigate to the demo-eye-remote-control directory and run ./start.sh to launch the program.

cd demo-eye-remote-control/
./start.sh

User Guide¶

Basic Operation Flow¶

Start the Program: After launching, the program will automatically activate the camera and begin detection.
Load a Video: Click the “Select Video File” button to load the video you want to play.
Start Watching: The system will automatically control play/pause based on your gaze state.
Switch Modes: Use full-screen playback mode for a better viewing experience.

Interface Features¶

Full-Screen Mode: Press “F11” or click the full-screen button on the interface to enter full-screen mode.
Full-Screen Playback Mode: Plays the video in full screen and controls playback based on real-time detection results.
Camera Toggle: Turn the camera on or off at any time.
Detection Toggle: Manually enable or disable the eye detection feature.
Landmark Display: Visualize eye key points and detection results.

Control Logic Details¶

State	Behavior	Description
Looking at screen + Eyes open	Continue playing	System detects that you are watching
Eyes closed or gaze shifted	Auto pause	Pauses playback when leaving or closing eyes
Face leaves camera view	Auto pause	Pauses if no face is detected for over 1 second

FAQ & Troubleshooting¶

Camera Not Recognized¶

Symptom:

No available camera device found

Solution:

Check if the camera is properly connected to the USB port.
Use the following command to check if the camera is detected:

ls -la /dev/video*

Try a different USB port.
If the issue persists, use a powered USB hub.
Re-plug the USB camera.

“No module named cv2” Error When Running main.py¶

Symptom:

ModuleNotFoundError: No module named 'cv2'

Solution:

This usually means install.sh did not complete successfully. Return to the project root directory and re-run the installation script:

cd demo-eye-remote-control
./install.sh

Application Demo¶

eye_remote_control_en

Technical Support & Contributions¶

If you encounter any issues during use, feel free to submit a technical inquiry on the Quectel Official Forum. Our technical support team will respond promptly.

Open-source project repository: https://github.com/Quectel-Pi/demo-eye-remote-control

Issues and Pull Requests for bug reports and code contributions are welcome!